Snore acquisition system and earphone assembly

Abstract

The snore collection system comprises a control module, a collection module, a posture detection module, a heart rate detection module, a trigger module, a first analysis module and a second analysis module. The acquisition module, the posture detection module, the heart rate detection module and the trigger module are all in communication connection with the control module, and the first analysis module is in communication connection with the acquisition module, the posture detection module, the heart rate detection module and the control module; the second analysis module is in communication connection with the acquisition module and the control module. Compared with the prior art, by arranging the trigger module, the first analysis module and the second analysis module and utilizing a grading trigger mechanism, the function of collecting snore of a user in sleep with low power consumption is achieved, frequent false triggering of snore collection can be effectively reduced, the redundancy of snore data collection and the complexity of audio data processing are reduced, and the user experience is improved. The snore collection accuracy and efficiency are improved, and the power consumption of the earphone snore collection function is reduced.

Description

Technical Field

[0001] This invention relates to the field of headphone technology, and in particular to a snoring sound acquisition system and headphone components. Background Technology

[0002] With the continuous development of electronic technology, users have increasingly higher demands for headphone functionality. Existing headphones have been developed with health monitoring functions, such as heart rate monitoring and sleep quality analysis. For headphones equipped with sleep quality analysis, they typically monitor the user's snoring during sleep. In current technology, headphones usually directly collect ambient audio signals and analyze all audio signals to extract the user's snoring. This method of snoring acquisition has high power consumption, redundant data, and low processing efficiency.

[0003] Therefore, it is necessary to provide a snoring sound acquisition system and headphone assembly to solve the above problems. Summary of the Invention

[0004] This invention provides a snoring sound acquisition system and headphones, which can effectively solve the problems of excessive power consumption, redundant acquisition data, and low processing efficiency in headphones for snoring sound acquisition.

[0005] To achieve the above objectives, this invention proposes a snoring sound acquisition system, which includes a control module, an acquisition module, an attitude detection module, a heart rate detection module, a trigger module, a first analysis module, and a second analysis module. The acquisition module, attitude detection module, heart rate detection module, and trigger module are all communicatively connected to the control module. The first analysis module is communicatively connected to the acquisition module, attitude detection module, heart rate detection module, and control module. The second analysis module is communicatively connected to the acquisition module and control module.

[0006] In a preferred embodiment, the triggering module includes a first acquisition unit and a first determination unit, wherein the first acquisition unit is communicatively connected to the control module, and the first determination unit is communicatively connected to the first acquisition unit and the control module.

[0007] In a preferred embodiment, the first analysis module includes a first extraction unit, a fusion unit, and a first analysis unit; the first extraction unit is communicatively connected to the acquisition module, the attitude detection module, and the heart rate detection module, respectively; the fusion unit is communicatively connected to the first extraction unit; and the first analysis unit is communicatively connected to the fusion unit.

[0008] In a preferred embodiment, the first extraction unit includes a first interception subunit and a first extraction subunit; the first interception subunit is communicatively connected to the acquisition module, the attitude detection module and the heart rate detection module, and the first extraction subunit is communicatively connected to the first interception subunit.

[0009] In a preferred embodiment, the fusion unit includes a first fusion subunit and a second fusion subunit; the first fusion subunit is communicatively connected to the first extraction unit, and the second fusion subunit is communicatively connected to the first fusion subunit.

[0010] In a preferred embodiment, the first analysis unit includes a first analysis subunit and a first mapping subunit; the first analysis subunit is communicatively connected to the fusion unit, and the first mapping subunit is communicatively connected to the first analysis subunit.

[0011] In a preferred embodiment, the second analysis module includes a second extraction unit and a second analysis unit; the second extraction unit is communicatively connected to the acquisition module, and the second analysis unit is communicatively connected to the second extraction unit.

[0012] In a preferred embodiment, the second extraction unit includes a second interception subunit and a second extraction subunit; the second interception subunit is communicatively connected to the acquisition module, and the second extraction subunit is communicatively connected to the second interception subunit.

[0013] In a preferred embodiment, the second analysis unit includes a second analysis subunit and a second mapping subunit; the second analysis subunit is communicatively connected to the second extraction unit; and the second mapping subunit is communicatively connected to the second analysis subunit.

[0014] The present invention also provides an earphone that includes the snoring sound acquisition system of any of the above claims.

[0015] The beneficial effects of this invention are as follows: by setting up a trigger module, a first analysis module and a second analysis module, and utilizing a hierarchical triggering mechanism, it can achieve the function of collecting snoring sounds during user sleep with low power consumption. This can effectively reduce the frequent false triggering of snoring sound collection, reduce the redundancy of snoring sound data collection and the complexity of audio data processing, improve the accuracy and efficiency of snoring sound collection, and reduce the power consumption of the headphone snoring sound collection function. Attached Figure Description

[0016] Figure 1 This is a first schematic diagram of the snoring sound acquisition system provided by the present invention;

[0017] Figure 2 This is a second schematic diagram of the snoring sound acquisition system provided by the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0020] It should also be noted that when a component is referred to as "fixed to" or "set on" another component, it can be directly on the other component or may have an intervening component present. When a component is referred to as "connected to" another component, it can be directly connected to the other component or may have an intervening component present.

[0021] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of a person skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0022] The following is the content of the first aspect of the present invention:

[0023] Please refer to Figure 1 In this embodiment, the snoring acquisition system includes a control module 1, an acquisition module 2, an attitude detection module 3, a heart rate detection module 4, a trigger module 5, a first analysis module 6, and a second analysis module 7.

[0024] The system comprises the following modules: Control Module 1 receives and processes signals to output feedback signals and parameter information for controlling the operation of other modules. Acquisition Module 2 is a microphone array within the earphones, used to acquire ambient audio signals from the current environment. Posture Detection Module 3 is a posture detection sensor within the earphones, used to acquire posture signals corresponding to the user's current posture state, including but not limited to lying, walking, and running. Heart Rate Detection Module 4 is a heart rate sensor within the earphones, used to acquire the user's heart rate signal in the current state. Trigger Module 5 detects whether sleep analysis is triggered. First Analysis Module 6 analyzes and determines whether to activate sleep acquisition mode. Second Analysis Module 7 analyzes and determines whether to activate snoring acquisition.

[0025] The acquisition module 2, attitude detection module 3, heart rate detection module 4 and trigger module 5 are all communicatively connected to the control module 1. The first analysis module 6 is communicatively connected to the acquisition module 2, attitude detection module 3, heart rate detection module 4 and control module 1. The second analysis module 7 is communicatively connected to the acquisition module 2 and control module 1.

[0026] Before triggering the collection of snoring sounds during a user's sleep, it is necessary to determine whether the user is asleep. Therefore, sleep analysis needs to be triggered first. After triggering sleep analysis, if the user is detected to be asleep, the sleep collection mode is activated. In the sleep collection mode of the headphones, the headphones collect ambient audio signals with low power consumption and perform targeted analysis based on snoring characteristics. When snoring is detected, the audio signals from the user's mouth and nose are collected in a targeted manner.

[0027] Specifically, control module 1 activates trigger module 5, which acquires the current time information and preset specific time information. This specific time information can be a user-defined time period or a pre-set time period within the system, selectable according to design requirements. Trigger module 5 determines whether the current time information falls within the specific time period; if so, it outputs a first trigger signal to control module 1 to initiate sleep analysis.

[0028] After receiving the first trigger signal, control module 1 activates acquisition module 2, posture detection module 3, heart rate detection module 4, and first analysis module 6. Acquisition module 2 acquires the ambient audio signal of the current scene and outputs it to the first analysis module 6; posture detection module 3 acquires the user's current posture signal and outputs it to the first analysis module 6; heart rate detection module 4 acquires the user's current heart rate signal and outputs it to the first analysis module 6. The acquisition cycle of acquisition module 2, posture detection module 3, and heart rate detection module 4 can be continuous or periodic, depending on the actual design requirements. Preferably, periodic acquisition is used to reduce data redundancy, decrease data processing complexity, and effectively reduce headphone power consumption.

[0029] After acquiring the ambient audio signal, posture signal, and heart rate signal, the first analysis module 6 preprocesses these signals. Following this preprocessing, it extracts the corresponding noise intensity features, posture features, and heart rate features from each signal, and then analyzes and infers these features to determine the probability of the user falling asleep in their current state. If the probability of falling asleep meets preset requirements, the first analysis module 6 outputs a signal to the control module 1 to activate the sleep acquisition mode.

[0030] After determining that the sleep acquisition mode has been triggered, control module 1 activates acquisition module 2 and second analysis module 7. Acquisition module 2 acquires the ambient audio signal of the current scene where the headphones are located and outputs the ambient audio signal to second analysis module 7. Second analysis module 7 preprocesses and transforms the ambient audio signal to obtain the ambient audio spectrum, then obtains a specific spectrum related to snoring from the ambient audio spectrum, then obtains the required target features from the specific spectrum, and then performs inference analysis on the target features to determine the probability of snoring events. If the probability of snoring events meets the preset requirements, second analysis module 7 outputs a signal to control module 1 to start snoring acquisition. After receiving the signal to start snoring acquisition, control module 1 controls acquisition module 2 to directionally acquire the audio signal from the user's mouth and nose.

[0031] Understandably, by setting up trigger module 5, first analysis module 6 and second analysis module 7, and utilizing a hierarchical triggering mechanism, the function of collecting snoring sounds during user sleep with low power consumption can be realized. This can effectively reduce frequent false triggers of snoring sound collection, reduce the redundancy of snoring sound data collection and the complexity of audio data processing, improve the accuracy and efficiency of snoring sound collection, and reduce the power consumption of the headphone snoring sound collection function.

[0032] For further details, please refer to... Figure 2 In one embodiment, the triggering module 5 includes a first acquisition unit 51 and a first determination unit 52. The first acquisition unit 51 is communicatively connected to the control module 1, and the first determination unit 52 is communicatively connected to the first acquisition unit 51 and the control module 1.

[0033] The first acquisition unit 51 is used to acquire current time information and preset specific time information. The first determination unit 52 is used to determine whether the current time information triggers sleep analysis.

[0034] Specifically, after the control module 1 starts the trigger module 5, the first acquisition unit 51 acquires the current time information and the preset specific time information, and outputs the obtained current time information and specific time information to the first determination unit 52. The first determination unit 52 compares the current time information with the start time and end time of the specific time information respectively.

[0035] If the current time information falls within a specific time frame, it indicates that the current time period can trigger sleep analysis. In this case, the first determination unit 52 outputs a first determination signal to the control module 1. Upon receiving the first determination signal, the control module 1 initiates sleep analysis and activates the corresponding module.

[0036] Understandably, by setting up the first acquisition unit 51 and the first determination unit 52, the user's needs can be better met and actual usage scenarios can be addressed. At the same time, by using time determination to trigger sleep analysis, the trigger detection of sleep analysis is achieved in a relatively simple way, reducing the power consumption of the headphones.

[0037] For further details, please refer to... Figure 2 In one embodiment, the first analysis module 6 includes a first extraction unit 61, a fusion unit 62, and a first analysis unit 63; the first extraction unit 61 is communicatively connected to the acquisition module 2, the attitude detection module 3, and the heart rate detection module 4, respectively; the fusion unit 62 is communicatively connected to the first extraction unit 61; and the first analysis unit 63 is communicatively connected to the fusion unit 62.

[0038] The first extraction unit 61 is used to extract the required feature information from environmental audio signals, posture signals, and heart rate signals. The fusion unit 62 is used to fuse the obtained feature information. The first analysis unit 63 is used to output the probability of falling asleep based on the feature information.

[0039] After triggering the sleep analysis, the control module 1 starts the first analysis module 6. The first extraction unit 61 acquires the environmental audio signal, posture signal and heart rate signal output by the acquisition module 2, posture detection module 3 and heart rate detection module 4 respectively, and preprocesses the environmental audio signal, posture signal and heart rate signal respectively. Then, based on the time dimension, the preprocessed environmental audio signal, posture signal and heart rate signal are segmented, and the required feature information is extracted from the segmented environmental audio signal, posture signal and heart rate signal respectively.

[0040] Specifically, feature information that can be extracted from environmental audio signals and used to construct noise intensity characteristics includes, but is not limited to, environmental noise level, noise stability, low-frequency energy proportion, and zero-crossing rate, which can be selected according to the actual design requirements. Feature information that can be extracted from posture signals and used to construct posture characteristics includes, but is not limited to, motion intensity, static proportion, posture stability, and rollover detection, which can be selected according to the design requirements. Feature information that can be extracted from heart rate signals and used to construct heart rate characteristics includes, but is not limited to, average heart rate, heart rate decline trend, and heart rate stability, which can be selected according to the actual design requirements.

[0041] In a preferred embodiment, the first extraction unit 61 includes a first interception subunit and a first extraction subunit; the first interception subunit is communicatively connected to the acquisition module 2, the attitude detection module 3 and the heart rate detection module 4, and the first extraction subunit is communicatively connected to the first interception subunit.

[0042] The first segmentation subunit is used to segment the environmental audio signal, attitude signal, and heart rate signal. The first extraction subunit is used to extract the required feature information from the segmented environmental audio signal, attitude signal, and heart rate signal.

[0043] Specifically, after preprocessing the environmental audio signal, posture signal, and heart rate signal, the first segmentation subunit segments these signals into several segments based on time. The segmentation duration can be set according to the acquisition time of the environmental audio signal, posture signal, and heart rate signal, and can be adjusted according to actual design requirements; no limitation is made here. The first segmentation subunit then outputs the segmented signals to the first extraction subunit, which then extracts the required noise intensity features, posture features, and heart rate features. It is easy to understand that segmenting the environmental audio signal, posture signal, and heart rate signal based on the time dimension improves the smoothness of subsequent feature fusion.

[0044] After the first extraction unit 61 obtains the required feature information, it inputs the extracted feature information into the fusion unit 62. After obtaining the noise intensity feature, posture feature and heart rate feature, the fusion unit 62 performs fusion and aggregation processing on the noise intensity feature, posture feature and heart rate feature based on preset weights and methods to obtain the required aggregated feature.

[0045] In a preferred embodiment, the fusion unit 62 includes a first fusion subunit and a second fusion subunit; the first fusion subunit is communicatively connected to the first extraction unit 61, and the second fusion subunit is communicatively connected to the first fusion subunit.

[0046] The first fusion subunit is used to fuse feature information from the same time period to obtain a comprehensive feature. The second fusion subunit is used to aggregate the obtained comprehensive features.

[0047] After the first extraction unit 61 outputs the extracted feature information to the fusion unit 62, the first fusion subunit fuses the noise intensity features, posture features, and heart rate features from the same time period according to a preset weight to obtain a comprehensive feature. This preset weight can be set according to the actual design requirements. After obtaining several comprehensive features, the first fusion subunit outputs the obtained comprehensive features to the second fusion subunit. The second fusion subunit, after obtaining several comprehensive features, then aggregates these comprehensive features to obtain an aggregated feature.

[0048] Understandably, by setting the first fusion subunit and the second fusion subunit, aggregated features that better fit the characteristics of sleep persistence can be obtained, improving the smoothness of feature information, reducing the impact of abrupt changes in feature information on sleep analysis, and to a certain extent improving the accuracy of the probability of sleep events output by the subsequent sleep analysis model.

[0049] After obtaining the aggregated features, the fusion unit 62 outputs the aggregated features to the first analysis unit 63. The first analysis unit 63 analyzes and infers the obtained aggregated features and outputs the corresponding sleep event probabilities. Specifically, the first analysis unit 63 includes a first analysis subunit and a first mapping subunit; the first analysis subunit is communicatively connected to the fusion unit 62, and the first mapping subunit is communicatively connected to the first analysis subunit.

[0050] The first analysis subunit is used to reason about and analyze aggregated features to obtain the corresponding target score. The first mapping unit is used to map the target score to obtain the probability of falling asleep.

[0051] After the fusion unit 62 outputs the aggregated features to the first analysis unit 63, the first analysis subunit performs inference analysis on the aggregated features. Specifically, the first analysis subunit performs multiple local inference analyses on the aggregated features based on the aggregated nodes and outputs corresponding specific scores. After obtaining several specific scores, it calculates the average of these scores to obtain the target score. After obtaining the target score, the first analysis subunit outputs the target score to the first mapping subunit, which maps and transforms the target score according to a preset activation function to obtain the probability of falling asleep.

[0052] It is understandable that a user's sleep state is a continuous process rather than an instantaneous state. By setting up the first extraction unit 61, the fusion unit 62, and the first analysis unit 63, inference analysis of aggregated features can be realized to achieve smooth inference analysis of feature information in multiple time periods. This can effectively reduce instantaneous misjudgment in sleep analysis, improve the output accuracy of sleep analysis, and effectively optimize the computational load of inference while maintaining relatively high analysis accuracy, thereby reducing the power consumption of the headphones.

[0053] For further details, please refer to... Figure 2 In one embodiment, the second analysis module 7 includes a second extraction unit 71 and a second analysis unit 72; the second extraction unit 71 is communicatively connected to the acquisition module 2, and the second analysis unit 72 is communicatively connected to the second extraction unit 71.

[0054] The second extraction unit 71 is used to extract the desired target features from the environmental audio signal. The second analysis unit 72 is used to analyze and infer the target features to output the corresponding snoring event probability.

[0055] Specifically, after the first analysis module 6 outputs a signal to the control module 1 to start the sleep acquisition mode, the control module 1 activates the acquisition module 2 and the second analysis module 7. The acquisition module 2 acquires the ambient audio signal of the current scene of the headphones and outputs the ambient audio signal to the second analysis module 7. The second extraction unit 71 acquires the ambient audio signal and preprocesses and transforms it to obtain the ambient audio spectrum. The second extraction unit 71 then truncates the audio spectrum according to the preset target bandwidth of the snoring feature to obtain the required target spectrum. After obtaining the required target spectrum, the second extraction unit 71 extracts the required target features from the target spectrum.

[0056] In a preferred embodiment, the second extraction unit 71 includes a second truncation subunit and a second extraction subunit; the second truncation subunit is communicatively connected to the acquisition module 2, and the second extraction subunit is communicatively connected to the second truncation subunit. The second truncation subunit is used to truncate the desired target spectrum from the audio spectrum. The second extraction subunit is used to extract the desired target features from the target spectrum. Specifically, the desired feature information can be extracted from multiple aspects such as the spectral envelope shape features, harmonic features, energy features, and spectral complexity features of the audio spectrum as target features.

[0057] After preprocessing and converting the ambient audio signal to obtain the ambient audio spectrum, the second extraction subunit extracts a spectrum from the ambient audio spectrum according to a pre-set target bandwidth to obtain the desired target spectrum. The second extraction subunit outputs the obtained target spectrum to the second extraction subunit, which extracts the desired target features from the target spectrum based on the audio characteristics of snoring and the requirement for low power consumption.

[0058] Understandably, by setting up a second interception subunit and a second extraction subunit, and by intercepting the target spectrum from the ambient audio spectrum and then combining the characteristics of snoring with the requirements for low power consumption, the target features used for snoring recognition are ensured to be adaptable and accurate. At the same time, the amount of data processing is reduced to a large extent, thereby reducing the power consumption of the headphones.

[0059] The second extraction unit 71 outputs the extracted target features to the second analysis unit 72. The second analysis unit 72 then performs reasoning analysis on the target features according to the preset reasoning analysis process to obtain the total score of the target features. The total score is then converted to obtain the probability of the snoring event.

[0060] In a preferred embodiment, the second analysis unit 72 includes a second analysis subunit and a second mapping subunit; the second analysis subunit is communicatively connected to the second extraction unit 71; and the second mapping subunit is communicatively connected to the second analysis subunit.

[0061] The second analysis subunit is used to reason about the target features obtained from the analysis to obtain the total score. The second mapping subunit is used to map and transform the total score to output the probability of snoring events.

[0062] After the target features are input into the second analysis unit 72 by the second extraction unit 71, the second analysis subunit performs reasoning analysis on the target features according to a preset reasoning process to obtain the total score. Specifically, the second analysis subunit has several decision tree nodes pre-set. The target features pass through several decision tree nodes in sequence to obtain several sub-scores. After obtaining several sub-scores, all the obtained sub-scores are accumulated to obtain the total score.

[0063] The second analysis subunit outputs the obtained total score to the second mapping subunit, which then converts the total score to obtain the snoring event probability. When the snoring event probability meets the preset requirements, it indicates that the user is currently snoring. The second analysis unit 72 outputs a snoring acquisition signal to the control module 1. After receiving the snoring acquisition signal, the control module 1 starts the acquisition module 2 to directionally acquire the audio signal from the user's mouth and nose.

[0064] Understandably, by setting up a second analysis subunit and a second mapping subunit, the accuracy of snoring recognition is improved. At the same time, the dual simplification of target feature and snoring inference analysis can effectively reduce the amount of data processing and processing difficulty, reduce the chip's computing power consumption, and thus reduce the power consumption of the headphones.

[0065] In summary, this application, by setting up a trigger module 5, a first analysis module 6, and a second analysis module 7, utilizes a hierarchical triggering mechanism to achieve low-power acquisition of snoring sounds during user sleep. This effectively reduces frequent false triggers in snoring sound acquisition, reduces the redundancy of snoring sound data acquisition and the complexity of audio data processing, improves the accuracy and efficiency of snoring sound acquisition, and reduces the power consumption of the headphone snoring sound acquisition function.

[0066] The following is a second aspect of the present invention:

[0067] The present invention also provides an earphone assembly including the snoring acquisition system of any of the above embodiments, which realizes the function of acquiring snoring during sleep with low power consumption, effectively reducing the frequent false triggering of snoring acquisition, reducing the redundancy of snoring data acquisition and the complexity of audio data processing, improving the accuracy and efficiency of snoring acquisition, and reducing the power consumption of the earphone snoring acquisition function.

[0068] The above are only some or preferred embodiments of the present invention. Neither the text nor the drawings should limit the scope of protection of the present invention. All equivalent structural transformations made using the content of the present invention's specification and drawings under the overall concept of the present invention, or direct / indirect applications in other related technical fields, are included within the scope of protection of the present invention.

Claims

1. A snoring sound acquisition system, characterized by The snoring sound collecting system comprises a control module, a collecting module, a posture detecting module, a heart rate detecting module, a triggering module, a first analyzing module and a second analyzing module.

2. The snoring sound acquisition system of claim 1, wherein, The triggering module comprises a first obtaining unit and a first determining unit.

3. The snoring sound acquisition system of claim 1, wherein, The first analyzing module comprises a first extracting unit, a fusion unit and a first analyzing unit.

4. The snoring sound acquisition system of claim 3, wherein, The first extracting unit comprises a first intercepting subunit and a first extracting subunit.

5. The snoring sound acquisition system of claim 3, wherein, The fusion unit comprises a first fusion subunit and a second fusion subunit.

6. The snoring sound acquisition system of claim 3, wherein, The first analyzing unit comprises a first analyzing subunit and a first mapping subunit.

7. The snoring sound acquisition system of claim 1, wherein, The second analyzing module comprises a second extracting unit and a second analyzing unit.

8. The snoring sound acquisition system of claim 7, wherein, The second extracting unit comprises a second intercepting subunit and a second extracting subunit.

9. The snoring sound acquisition system of claim 1, wherein, The second analyzing unit comprises a second analyzing subunit and a second mapping subunit.

10. An earphone assembly, characterized by The snoring sound collecting system comprises the snoring sound collecting system according to any one of claims 1 to 9.

Images